Food Industry Sales Prediction : A Big Data Analysis & Sales Forecast of Bake-off Products

Abstract: In this thesis, the sales of bread and coffee bread at Coop Värmland AB have been studied. The aim was to find what factors that are important for the sales and then make predictions of how the sales will look like in the future to reduce waste and increase profits. Big data analysis and data exploration was used to get to know the data and find the factors that affect the sales the most. Time series forecasting and supervised machine learning models were used to predict future sales. The main focus was five different models that were compared and analysed, they were; Decision tree regression, Random forest regression, Artificial neural networks, Recurrent neural networks and a time series model called Prophet. Comparing the observed values to the predictions made by the models indicated that using a model based on the time series is to be preferred, that is, Prophet and Recurrent neural network. These two models gave the lowest errors and by that, the most accurate results. Prophet yielded mean absolute percentage errors of 8.295% for bread and 9.156% for coffee bread. The Recurrent neural network gave mean absolute percentage errors of 7.938% for bread and 13.12% for coffee bread. That is about twice as good as the models they are using today at Coop which are based on the mean value of the previous sales.